fudan-generative-vision/hallo
Audio-driven synthesis for portrait image animation
View on index · View in 3D Map
Related repos
- Generates long 4K portrait animations from a single image and audio, with optional text prompts for expression control
- audio-driven talking head video generation using diffusion models
- Generative engine for creating interactive 3D worlds
- Generates facial animation from audio
- Native multimodal model for image generation
- audio-driven portrait animation with editable facial landmarks
- animate portraits with fine-grained control over head, mouth, and eyes
- Animates portrait images for live streaming
- audio foundation model for understanding, generation, and conversation
- Generates binaural audio from video and text
